CRM
Backfill Intercom conversation topics onto stale HubSpot contacts
Finds HubSpot contacts with no recent Intercom topic, pulls their conversation history from Intercom, classifies the dominant topic with OpenAI.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule fires the backfill run
- ActionQuery HubSpot for contacts missing a fresh topicHubSpot
- LogicSkip contacts with no Intercom conversations
- ActionPull recent conversation transcripts from IntercomIntercom
- ActionClassify dominant topic with OpenAIOpenAI
- LogicDrop low-confidence topic labels
- OutputWrite topic + timestamp to HubSpot contactHubSpot
What it does
Many HubSpot contacts carry no signal about what they actually talk to support about. This workflow walks contacts whose `last_intercom_topic` property is empty or older than 90 days, fetches their Intercom conversation transcripts, and uses OpenAI to label the single dominant topic (e.g. "billing dispute", "onboarding", "API integration"). The result is written back to HubSpot so segmentation and routing reflect real conversation content.
When to use it
Run this when your CRM segments are decaying because topic data was never captured, or after migrating support tooling left a backlog of un-tagged contacts. Ideal as a one-time backfill plus a monthly catch-up on stale records.
How it works
A daily schedule fires the run. The workflow queries HubSpot for contacts missing a fresh topic, then for each one pulls the last 10 Intercom conversations. A logic step skips contacts with zero conversations. OpenAI reads the merged transcripts and returns one canonical topic plus a confidence score. A filter drops low-confidence labels, and the final step patches the HubSpot contact's `last_intercom_topic` and `topic_updated_at` properties.
Set it up
What you configure once, before turning it on.
- 1Connect HubSpotCRM, deals, marketing, support.
- 2Connect IntercomConversations, contacts, articles.
- 3Connect OpenAIModels, embeddings, files.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More CRM workflows
Daily orphaned-opportunity sweep with manager Slack digest
Each morning this scans Salesforce for open opportunities owned by inactive users and posts a per-manager digest in Slack listing the orphaned deals that need a new owner.
AI-Personalized Dormant Account Win-Back
On a dormancy anniversary, an agent researches the account's history and recent public signals, drafts a genuinely personalized win-back email.
Dormant Account Anniversary Re-engagement Email
Each day, finds Attio accounts whose last activity was exactly N months ago and sends each owner's contact a personalized re-engagement email from Gmail.
Dormant Account Check-In Call Scheduler
On the anniversary of an account's last touch, books a tentative check-in call on the owner's Google Calendar and emails the contact a scheduling invite.
Weekly Dormant-Anniversary Cohort Digest
Every week, groups dormant Attio accounts by which last-touch anniversary they hit that week, builds a prioritized digest.
Tag closed Intercom conversations onto Salesforce contacts in real time
On each Intercom conversation close, classifies the topic with OpenAI and appends it to the matching Salesforce contact's activity timeline so the topic never goes stale…
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.